Alert button
Picture for Prashanth Gurunath Shivakumar

Prashanth Gurunath Shivakumar

Alert button

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue

Jan 17, 2024
Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang, Yile Gu, Shalini Ghosh, Andreas Stolcke, Hung-yi Lee, Ivan Bulyko

Viaarxiv icon

Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks

Jan 05, 2024
Kevin Everson, Yile Gu, Huck Yang, Prashanth Gurunath Shivakumar, Guan-Ting Lin, Jari Kolehmainen, Ivan Bulyko, Ankur Gandhe, Shalini Ghosh, Wael Hamza, Hung-yi Lee, Ariya Rastrow, Andreas Stolcke

Viaarxiv icon

Discriminative Speech Recognition Rescoring with Pre-trained Language Models

Oct 10, 2023
Prashanth Gurunath Shivakumar, Jari Kolehmainen, Yile Gu, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

Figure 1 for Discriminative Speech Recognition Rescoring with Pre-trained Language Models
Figure 2 for Discriminative Speech Recognition Rescoring with Pre-trained Language Models
Viaarxiv icon

Personalization for BERT-based Discriminative Speech Recognition Rescoring

Jul 13, 2023
Jari Kolehmainen, Yile Gu, Aditya Gourav, Prashanth Gurunath Shivakumar, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

Figure 1 for Personalization for BERT-based Discriminative Speech Recognition Rescoring
Figure 2 for Personalization for BERT-based Discriminative Speech Recognition Rescoring
Figure 3 for Personalization for BERT-based Discriminative Speech Recognition Rescoring
Figure 4 for Personalization for BERT-based Discriminative Speech Recognition Rescoring
Viaarxiv icon

Scaling Laws for Discriminative Speech Recognition Rescoring Models

Jun 27, 2023
Yile Gu, Prashanth Gurunath Shivakumar, Jari Kolehmainen, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

Figure 1 for Scaling Laws for Discriminative Speech Recognition Rescoring Models
Figure 2 for Scaling Laws for Discriminative Speech Recognition Rescoring Models
Figure 3 for Scaling Laws for Discriminative Speech Recognition Rescoring Models
Figure 4 for Scaling Laws for Discriminative Speech Recognition Rescoring Models
Viaarxiv icon

Distillation Strategies for Discriminative Speech Recognition Rescoring

Jun 15, 2023
Prashanth Gurunath Shivakumar, Jari Kolehmainen, Yile Gu, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

Figure 1 for Distillation Strategies for Discriminative Speech Recognition Rescoring
Figure 2 for Distillation Strategies for Discriminative Speech Recognition Rescoring
Figure 3 for Distillation Strategies for Discriminative Speech Recognition Rescoring
Figure 4 for Distillation Strategies for Discriminative Speech Recognition Rescoring
Viaarxiv icon

Phone Duration Modeling for Speaker Age Estimation in Children

Sep 03, 2021
Prashanth Gurunath Shivakumar, Somer Bishop, Catherine Lord, Shrikanth Narayanan

Figure 1 for Phone Duration Modeling for Speaker Age Estimation in Children
Figure 2 for Phone Duration Modeling for Speaker Age Estimation in Children
Figure 3 for Phone Duration Modeling for Speaker Age Estimation in Children
Figure 4 for Phone Duration Modeling for Speaker Age Estimation in Children
Viaarxiv icon

Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords

Feb 19, 2021
Prashanth Gurunath Shivakumar, Panayiotis Georgiou, Shrikanth Narayanan

Figure 1 for Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Figure 2 for Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Figure 3 for Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Figure 4 for Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Viaarxiv icon

End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study

Feb 19, 2021
Prashanth Gurunath Shivakumar, Shrikanth Narayanan

Figure 1 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 2 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 3 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 4 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Viaarxiv icon